Large language models (LLMs) have exhibited remarkable ability in code generation. However, generating the correct solution in a single attempt still remains a challenge. Prior works utilize verification properties in software engineering to verify and re-rank solutions in a majority voting manner. But the assumption behind them that generated verification properties have better qualities than solutions may not always hold. In this paper, we treat them equally as different perspectives of LLMs' reasoning processes. We propose the Multi-Perspective Self-Consistency (MPSC) framework incorporating both inter- and intra-consistency across outputs from multiple perspectives. Specifically, we prompt LLMs to generate diverse outputs from three perspectives, Solution, Specification and Test case, constructing a 3-partite graph. With two measure functions of consistency, we embed both inter- and intra-consistency information into the graph. The optimal choice of solutions is then determined based on analysis in the graph. MPSC significantly boosts performance of foundation models (ChatGPT in this paper) on various benchmarks, including HumanEval (+15.91%), MBPP (+6.43%) and CodeContests (+9.37%), even surpassing GPT-4.

翻译：大语言模型（LLMs）在代码生成方面展现出卓越能力。然而，单次尝试即生成正确解决方案仍具挑战。先前研究利用软件工程中的验证属性，以多数投票方式验证并重排序解决方案。但这些方法隐含的假设——生成的验证属性质量始终优于解决方案——未必恒成立。本文将其平等视为大语言模型推理过程的不同视角，提出融合多视角输出间一致性与视角内一致性的多视角自一致性（MPSC）框架。具体而言，我们提示大语言模型从解决方案、规约和测试用例三个视角生成多样化输出，构建三分图。通过两种一致性度量函数，我们将视角间与视角内一致性信息嵌入图中，进而基于图分析确定最优解决方案选择。MPSC显著提升了基础模型（本文以ChatGPT为例）在多项基准测试中的性能，包括HumanEval（+15.91%）、MBPP（+6.43%）和CodeContests（+9.37%），其表现甚至超越GPT-4。